collinear-ai/curator_evals_bench
收藏官方服务：
资源简介：
这是一个名为code_correctness的数据集，包含id、prompt、response、label和source五个字段。数据集分为默认split，共有1302个示例。该数据集用于代码正确性检查。
This is a dataset named code_correctness, which includes five fields: id, prompt, response, label, and source. The dataset is split into a default division, containing a total of 1302 examples. It is used for code correctness checking.
提供机构：
collinear-ai
